llm-finetuning
LLM fine-tuning expert for LoRA, QLoRA, dataset preparation, and training optimization
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 10-21 00:11
24,317 results
LLM fine-tuning expert for LoRA, QLoRA, dataset preparation, and training optimization
Master local LLM inference, model selection, VRAM optimization, and local deployment using Ollama, llama.cpp, vLLM, and LM Studio. Expert in quantization…
Manage local skills - list, add, remove, search, edit, setup wizard
Use when an agent needs to understand or set its Tariboy Goal and AI usage attribution.
Automate Instagram tasks via Rube MCP (Composio): create posts, carousels, manage media, get insights, and publishing limits. Always search tools first for…
Phone calling skill for OpenClaw: agent makes real outbound phone calls to users for alerts, briefings, reminders, and urgent notifications. Managed service,…
Use to stand up Omni-Channel setup headlessly on Salesforce: base settings, agent users, service channels, routing configs, queues (create and align) and…
Find and install skills from the Orthogonal skill library. Use when you need capabilities you don't have, want to discover available skills, or need to add new…
Use when writing nodes to Iskron — phenomena, kriyas, vimarshas, contours, roles. Triggers: "write", "record", "add node", "create kriya", "put into…
Transition from vibe coding (fast prototyping) to agentic engineering (rigorous iteration). Use this skill when the user has a rough prototype and wants to…
Builds and debugs Letta Code channels, including first-party channel adapters and dynamic user channel plugins under ~/.letta/channels. Use when adding…
Use when an evaluation run must merge research, findings, documentation, and repair outputs into one verified result.
Use the Alexa shopping assistant on Amazon's front end to initiate natural language Q&A and obtain shopping guidance answers related to the question, recommended product groups, ASIN lists, and follow-up questions that can be asked. Each call supports only 1 prompt; if a follow-up is needed, the agent must summarize the context and concatenate the new question to initiate a new request. A url can be used to supplement the Amazon page context. When the user mentions Amazon Alexa, Alexa...
OWASP Top 10 for LLM Applications (2025) knowledge base for identifying, assessing, and remediating large language model security risks.
The terminology layer for Web and mobile H5 — turn the interface description the user can't quite articulate into an accurate requirement that can be sent straight to an Agent, and casually point out the term for the thing they just described but couldn't name. **It applies to every round of conversation, not limited to a certain stage**: in any round of conversation, as long as the user describes a webpage or H5 in plain language…
Spawn background subagents for parallel or long-running tasks. Use when you need research threads, context isolation, or detached execution.
Comprehensive catalog of 500+ AI agent use cases across industries with open-source implementations and framework examples
Use when working with Anthropic Claude Agent SDK. Provides architecture guidance, implementation patterns, best practices, and common pitfalls.
Build MCP (Model Context Protocol) servers that give Claude new capabilities. Use when user wants to create an MCP server, add tools to Claude, or integrate…
Surface Claude s assumptions about a phase approach before planning
Switch model profile for GSD agents (quality balanced budget)
Export this agent's data into a migration bundle for import elsewhere. Use when moving an agent off Starchild or backing up state (e.g. export my memory and…
Implement the Syncfusion ASP.NET Core AI AssistView control for interactive AI-powered assistance interfaces. Use this skill when implementing AI assistants,…
Use this skill when the user is in the skill lifecycle: create a new skill from a workflow / template / process / decision pattern, improve an existing skill, independently optimize the trigger description of a skill, or audit skill compliance against writing principles. Trigger: "I want / help me make a skill for X" / "make one from scratch…